NURBGen: High-Fidelity Text-to-CAD Generation through LLM-Driven NURBS Modeling

2025-11-09

AI Summary

Existing text-to-CAD approaches struggle to generate editable, high-fidelity models—either producing non-editable meshes or relying on scarce design-history data. This paper introduces the first LLM-driven NURBS modeling framework that directly maps natural language descriptions to parametric NURBS surface representations and supports BRep export. Our method employs a hybrid geometric representation—combining untrimmed NURBS surfaces with analytically defined primitives—to enhance expressiveness for complex shapes while reducing sequence length. We integrate LLM fine-tuning, JSON-structured output generation, a Python-based BRep conversion interface, and an automated annotation pipeline. Evaluated on diverse textual inputs, our approach significantly outperforms state-of-the-art methods; expert validation confirms superior geometric fidelity and dimensional accuracy. To foster reproducibility and advancement, we publicly release the high-quality partABC dataset.

Technology Category

• Natural Language Processing: (Large) Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Large Vision Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Generating editable 3D CAD models from natural language remains challenging, as existing text-to-CAD systems either produce meshes or rely on scarce design-history data. We present NURBGen, the first framework to generate high-fidelity 3D CAD models directly from text using Non-Uniform Rational B-Splines (NURBS). To achieve this, we fine-tune a large language model (LLM) to translate free-form texts into JSON representations containing NURBS surface parameters ( extit{i.e}, control points, knot vectors, degrees, and rational weights) which can be directly converted into BRep format using Python. We further propose a hybrid representation that combines untrimmed NURBS with analytic primitives to handle trimmed surfaces and degenerate regions more robustly, while reducing token complexity. Additionally, we introduce partABC, a curated subset of the ABC dataset consisting of individual CAD components, annotated with detailed captions using an automated annotation pipeline. NURBGen demonstrates strong performance on diverse prompts, surpassing prior methods in geometric fidelity and dimensional accuracy, as confirmed by expert evaluations. Code and dataset will be released publicly.

Problem

• Generating editable CAD models from natural language descriptions
• Overcoming limitations of mesh outputs and scarce design-history data
• Translating free-form text into NURBS parameters for high-fidelity CAD

Innovation

• LLM translates text to NURBS parameters
• Hybrid representation combines NURBS with primitives
• Automated annotation pipeline creates partABC dataset